This paper presents the application of a new technique based on the variance of three phase stator currents’ instantaneous variance (VIV-TPSC) to detect faults in induction motors. The proposed fault detection algorithm is based on computation of the confidence interval index (CI) at different load conditions. This index provides an estimate of the amount of error in the considered data and determines the accuracy of the computed statistical estimates. The algorithm offers the advantage of being able to detect faults, particularly broken rotor bars, independently of loading conditions. Moreover, the implementation of the algorithm requires only the calculation of the variance of the measured three-phase stator currents’ instantaneous variance. The discrimination between faulty and healthy operations is based on the adherence of VIV-TPSC value to the CI which is calculated after checking out that the variance of instantaneous variance is a random variable obeying to normal distribution law. Rotor and stator resistance values are not used in any part of the CI and VIV-TPSC calculations, giving the algorithm more robustness. The effectiveness and the accuracy of the proposed approach are shown under different faulty operations.
In this paper, a study has presented the performance of a neural networks technique to detect the broken rotor bars (BRBs) fault in induction motors (IMs). In this context, the fast Fourier transform (FFT) applied on Hilbert modulus obtained via the stator current signal has been used as a diagnostic signal to replace the FFT classic, the characteristics frequency are selected from the Hilbert modulus spectrum, in addition, the different load conditions are used as three inputs data for the neural networks. The efficiency of the proposed method is verified by simulation in MATLAB environment.
Purpose
The purpose of this study aims to focus on the detection and identification of the broken rotor bars (BRBs) of a squirrel cage induction motor (SCIM). The presented diagnosis technique is based on artificial neural networks (NNs) that use as inputs the results of the spectral analysis using the fast Fourier transform (FFT) of the reduced Park’s vector modulus (RPVM), along with the load values in which the motor operates.
Design/methodology/approach
First, this paper presents a comparative study between FFT applied on Hilbert modulus, Park’s vector modulus and RPVM to extract feature frequencies of BRB faults. Moreover, the extracted features of FFT applied to RPVM and the load values were selected as NNs’ inputs for the detection of the number of BRBs.
Findings
The obtained simulation results using MATLAB (Matrix Laboratory) environment show the effectiveness and accuracy of the proposed NNs based approach.
Originality/value
The current paper presents a novel diagnostic method for BRBs’ fault detection in SCIM, based on the combination between the signal processing analysis (FFT of RPVM) and artificial intelligence (NNs).
In this paper, a fault detection and diagnosis system for induction motors using motor current signature analysis and the Fuzzy Min-Max (FMM) neural network is described. The finite element method is first employed to generate experimental data for predicting the changes in stator current signatures of an induction motor due to broken rotor bars. Then, a series real laboratory experiments is for broken rotor bars detection and diagnosis. The induction motor with broken rotor bars is operated under different load conditions. In all the experiments, the FMM network is used to learn and distinguish between normal and faulty states of the induction motor based on the input features extracted from the power spectral density. The experimental results positively demonstrate that the FMM network is useful for fault detection and diagnosis of broken rotor bars in induction motors.
Induction Motor Faults Detection Using a Statistical Procedure Based-Approach
